© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 19-GEMMASCOPE-RES-16K
    6. 2422
    Prev
    Next
    INDEX
    Explanations

    technical terms and measurements related to physics or engineering concepts, especially those involving circular shapes or spatial dimensions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Stair
    -0.54
    romyalgia
    -0.48
    LONG
    -0.47
     Stair
    -0.47
    long
    -0.46
     stair
    -0.46
     long
    -0.46
     ארו
    -0.46
     iceberg
    -0.46
     strop
    -0.45
    POSITIVE LOGITS
     radius
    1.72
     diameter
    1.63
     Diameter
    1.52
    radius
    1.50
    diameter
    1.47
     radii
    1.44
     Radius
    1.43
     circle
    1.41
    Diameter
    1.41
    Radius
    1.40
    Activations Density 0.511%

    No Known Activations